AI agents call watchers.prediction-market to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves information about Polymarket outcomes via callback registration. While it operates within a financial domain (prediction markets), it does not move money, execute trades, modify market data, or create financial obligations. It is fundamentally a read operation that registers to receive data updates.
From the tool's definition Tool description states 'get a signed callback when a Polymarket outcome' — this is a read/query operation that retrieves or polls prediction market data and sets up a notification mechanism.
Attacks that exploit this kind of access
WATCHER: get a signed callback when a Polymarket outcome\. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for watchers.prediction-market: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
watchers.prediction-market is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the watchers.prediction-market rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for watchers.prediction-market. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
watchers.prediction-market is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →